Files
linux/arch/arm64/include/asm/io.h
Mark Rutland d044d6ba6f arm64: io: permit offset addressing
Currently our IO accessors all use register addressing without offsets,
but we could safely use offset addressing (without writeback) to
simplify and optimize the generated code.

To function correctly under a hypervisor which emulates IO accesses, we
must ensure that any faulting/trapped IO access results in an ESR_ELx
value with ESR_ELX.ISS.ISV=1 and with the tranfer register described in
ESR_ELx.ISS.SRT. This means that we can only use loads/stores of a
single general purpose register (or the zero register), and must avoid
writeback addressing modes. However, we can use immediate offset
addressing modes, as these still provide ESR_ELX.ISS.ISV=1 and a valid
ESR_ELx.ISS.SRT when those accesses fault at Stage-2.

Currently we only use register addressing without offsets. We use the
"r" constraint to place the address into a register, and manually
generate the register addressing by surrounding the resulting register
operand with square braces, e.g.

| static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr)
| {
|         asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
| }

Due to this, sequences of adjacent accesses need to generate addresses
using separate instructions. For example, the following code:

| void writeq_zero_8_times(void *ptr)
| {
|        writeq_relaxed(0, ptr + 8 * 0);
|        writeq_relaxed(0, ptr + 8 * 1);
|        writeq_relaxed(0, ptr + 8 * 2);
|        writeq_relaxed(0, ptr + 8 * 3);
|        writeq_relaxed(0, ptr + 8 * 4);
|        writeq_relaxed(0, ptr + 8 * 5);
|        writeq_relaxed(0, ptr + 8 * 6);
|        writeq_relaxed(0, ptr + 8 * 7);
| }

... is compiled to:

| <writeq_zero_8_times>:
|     str     xzr, [x0]
|     add     x1, x0, #0x8
|     str     xzr, [x1]
|     add     x1, x0, #0x10
|     str     xzr, [x1]
|     add     x1, x0, #0x18
|     str     xzr, [x1]
|     add     x1, x0, #0x20
|     str     xzr, [x1]
|     add     x1, x0, #0x28
|     str     xzr, [x1]
|     add     x1, x0, #0x30
|     str     xzr, [x1]
|     add     x0, x0, #0x38
|     str     xzr, [x0]
|     ret

As described above, we could safely use immediate offset addressing,
which would allow the ADDs to be folded into the address generation for
the STRs, resulting in simpler and smaller generated assembly. We can do
this by using the "o" constraint to allow the compiler to generate
offset addressing (without writeback) for a memory operand, e.g.

| static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr)
| {
|         volatile u64 __iomem *ptr = addr;
|         asm volatile("str %x0, %1" : : "rZ" (val), "o" (*ptr));
| }

... which results in the earlier code sequence being compiled to:

| <writeq_zero_8_times>:
|     str     xzr, [x0]
|     str     xzr, [x0, #8]
|     str     xzr, [x0, #16]
|     str     xzr, [x0, #24]
|     str     xzr, [x0, #32]
|     str     xzr, [x0, #40]
|     str     xzr, [x0, #48]
|     str     xzr, [x0, #56]
|     ret

As Will notes at:

  https://lore.kernel.org/linux-arm-kernel/20240117160528.GA3398@willie-the-truck/

... some compilers struggle with a plain "o" constraint, so it's
preferable to use "Qo", where the additional "Q" constraint permits
using non-offset register addressing.

This patch modifies our IO write accessors to use "Qo" constraints,
resulting in the better code generation described above. The IO read
accessors are left as-is because ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE
requires that non-offset register addressing is used, as the LDAR
instruction does not support offset addressing.

When compiling v6.8-rc1 defconfig with GCC 13.2.0, this saves ~4KiB of
text:

| [mark@lakrids:~/src/linux]% ls -al vmlinux-*
| -rwxr-xr-x 1 mark mark 153960576 Jan 23 12:01 vmlinux-after
| -rwxr-xr-x 1 mark mark 153862192 Jan 23 11:57 vmlinux-before
|
| [mark@lakrids:~/src/linux]% size vmlinux-before vmlinux-after
|    text    data     bss     dec     hex filename
| 26708921        16690350         622736 44022007        29fb8f7 vmlinux-before
| 26704761        16690414         622736 44017911        29fa8f7 vmlinux-after

... though due to internal alignment of sections, this has no impact on
the size of the resulting Image:

| [mark@lakrids:~/src/linux]% ls -al Image-*
| -rw-r--r-- 1 mark mark 43590144 Jan 23 12:01 Image-after
| -rw-r--r-- 1 mark mark 43590144 Jan 23 11:57 Image-before

Aside from the better code generation, there should be no functional
change as a result of this patch. I have lightly tested this patch,
including booting under KVM (where some devices such as PL011 are
emulated).

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20240124111259.874975-1-mark.rutland@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2024-02-20 18:08:37 +00:00

190 lines
5.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/io.h
*
* Copyright (C) 1996-2000 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_IO_H
#define __ASM_IO_H
#include <linux/types.h>
#include <linux/pgtable.h>
#include <asm/byteorder.h>
#include <asm/barrier.h>
#include <asm/memory.h>
#include <asm/early_ioremap.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
/*
* Generic IO read/write. These perform native-endian accesses.
*/
#define __raw_writeb __raw_writeb
static __always_inline void __raw_writeb(u8 val, volatile void __iomem *addr)
{
volatile u8 __iomem *ptr = addr;
asm volatile("strb %w0, %1" : : "rZ" (val), "Qo" (*ptr));
}
#define __raw_writew __raw_writew
static __always_inline void __raw_writew(u16 val, volatile void __iomem *addr)
{
volatile u16 __iomem *ptr = addr;
asm volatile("strh %w0, %1" : : "rZ" (val), "Qo" (*ptr));
}
#define __raw_writel __raw_writel
static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr)
{
volatile u32 __iomem *ptr = addr;
asm volatile("str %w0, %1" : : "rZ" (val), "Qo" (*ptr));
}
#define __raw_writeq __raw_writeq
static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr)
{
volatile u64 __iomem *ptr = addr;
asm volatile("str %x0, %1" : : "rZ" (val), "Qo" (*ptr));
}
#define __raw_readb __raw_readb
static __always_inline u8 __raw_readb(const volatile void __iomem *addr)
{
u8 val;
asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
"ldarb %w0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
#define __raw_readw __raw_readw
static __always_inline u16 __raw_readw(const volatile void __iomem *addr)
{
u16 val;
asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
"ldarh %w0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
#define __raw_readl __raw_readl
static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
{
u32 val;
asm volatile(ALTERNATIVE("ldr %w0, [%1]",
"ldar %w0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
#define __raw_readq __raw_readq
static __always_inline u64 __raw_readq(const volatile void __iomem *addr)
{
u64 val;
asm volatile(ALTERNATIVE("ldr %0, [%1]",
"ldar %0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
/* IO barriers */
#define __io_ar(v) \
({ \
unsigned long tmp; \
\
dma_rmb(); \
\
/* \
* Create a dummy control dependency from the IO read to any \
* later instructions. This ensures that a subsequent call to \
* udelay() will be ordered due to the ISB in get_cycles(). \
*/ \
asm volatile("eor %0, %1, %1\n" \
"cbnz %0, ." \
: "=r" (tmp) : "r" ((unsigned long)(v)) \
: "memory"); \
})
#define __io_bw() dma_wmb()
#define __io_br(v)
#define __io_aw(v)
/* arm64-specific, don't use in portable drivers */
#define __iormb(v) __io_ar(v)
#define __iowmb() __io_bw()
#define __iomb() dma_mb()
/*
* I/O port access primitives.
*/
#define arch_has_dev_port() (1)
#define IO_SPACE_LIMIT (PCI_IO_SIZE - 1)
#define PCI_IOBASE ((void __iomem *)PCI_IO_START)
/*
* String version of I/O memory access operations.
*/
extern void __memcpy_fromio(void *, const volatile void __iomem *, size_t);
extern void __memcpy_toio(volatile void __iomem *, const void *, size_t);
extern void __memset_io(volatile void __iomem *, int, size_t);
#define memset_io(c,v,l) __memset_io((c),(v),(l))
#define memcpy_fromio(a,c,l) __memcpy_fromio((a),(c),(l))
#define memcpy_toio(c,a,l) __memcpy_toio((c),(a),(l))
/*
* I/O memory mapping functions.
*/
#define ioremap_prot ioremap_prot
#define _PAGE_IOREMAP PROT_DEVICE_nGnRE
#define ioremap_wc(addr, size) \
ioremap_prot((addr), (size), PROT_NORMAL_NC)
#define ioremap_np(addr, size) \
ioremap_prot((addr), (size), PROT_DEVICE_nGnRnE)
/*
* io{read,write}{16,32,64}be() macros
*/
#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(__v); __v; })
#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(__v); __v; })
#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(__v); __v; })
#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
#define iowrite64be(v,p) ({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
#include <asm-generic/io.h>
#define ioremap_cache ioremap_cache
static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size)
{
if (pfn_is_map_memory(__phys_to_pfn(addr)))
return (void __iomem *)__phys_to_virt(addr);
return ioremap_prot(addr, size, PROT_NORMAL);
}
/*
* More restrictive address range checking than the default implementation
* (PHYS_OFFSET and PHYS_MASK taken into account).
*/
#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
unsigned long flags);
#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap
#endif /* __ASM_IO_H */